Observed changes in Codex plugins
See what changed in descriptions, skills and files. Compare before-and-after snapshots and follow the plugins you care about.
Explore recent changes →Explore 5,822 plugins across 14 categories.
Follow up to 10 plugins for free. Newest means first added to our catalog, not the publisher’s release date.
All plugins 255
109–144 of 255All query words must match. Use quotes for an exact phrase. Matches include publisher text, keywords and attributed research.
| Plugin / developer | Category | Follow |
|---|---|---|
Andrej Karpathy SkillsRONALD FERRARI SOARES Publisher full description …rinciples inspired by Andrej Karpathy public guidance to help agents make smaller, safer, easier-to-review code changes. Show in context →2 more matching sources |
Developer ToolsVersion 1.0.0 | View details → |
Avoid AI WritingConor Bronsdon Publisher full description …and source facts, edit named files with narrow changes, and verify that protected material such as code, quotes, links, numbers, frontmatter, and tables survives the edit. The package keeps the original Avoid AI Writing skill intact and adds focused ChatGPT and Codex routing for detect-only review, voice-preserving rewrites, file edits, preservation checks, and false-positive review. Its signals are writing-quality indicators, not proof of AI authorship. Show in context →1 more matching sourcesPublisher capabilities · listing AI-pattern audit Detect-only review Voice-preserving rewrite Targeted file editing Preservation verification False-positive review Multi-step writing cleanup Show in context → |
ProductivityVersion 3.29.0 | View details → |
ChatPRDChatPRD Publisher description Write, review, and update product requirements documents with ChatPRD from ChatGPT, Codex, and Cursor. Draft PRDs from notes or code context with ChatPRD's templates (no account needed), critique specs, plan implementation from a PRD, and keep docs in sync with what shipped. Show in context →2 more matching sourcesPublisher full description …s. Draft PRDs, AI development briefs, user testing plans, and launch checklists from rough notes or code context using ChatPRD's built-in templates, with no account required: get the document as Markdown or save it to a connected tool like Notion or Google Drive. Review any doc with a ChatPRD scorecard (strategy, structure, clarity, completeness) and exact edit suggestions, or turn it into an interactive HTML page with diagrams and clickable prototypes. Connec… Show in context →Publisher capabilities · listing Browse templates Create interactive artifacts Review documents Search documents Read documents Create documents Update documents Show in context → |
ProductivityVersion 1.2.5 | View details → |
Flower상빈 박 Publisher full description …olicy, approval, idempotency, durable run state, and audit to business mutations. This plugin helps Codex set up, build, inspect, review, migrate, test, and verify either library or both together. Support and bug reports are handled in the Flower GitHub issue tracker. Show in context →1 more matching sources |
Developer ToolsVersion 0.3.3 | View details → |
GuardioGuardio Publisher full description Guardio helps you check suspicious links and understand your online protection from ChatGPT and Codex. Check a website before opening it, or check links extracted from a suspicious message without sending the message body to Guardio. Connect your Guardio account to review protection setup, scan activity, recent data leaks, linked-service counts, and security recommendations. You can also check whether an email address or phone number appears in known data breach… Show in context →2 more matching sourcesPublisher capabilities · listing Check suspicious links Check links in messages Look up known email and phone breaches Review account protection and scan activity Review security recommendations Set up browser protection Send requested product feedback Show in context →Publisher description Check suspicious links, review known data leaks, and understand your Guardio protection. Show in context → |
SecurityVersion 0.2.2 | View details → |
MollieMollieMollie payment integration — connects Codex to your Mollie account via the Mollie MCP server and activates skills for payments, Mollie Co... Publisher capabilities · listing …ent integrations Set up Mollie Connect for platforms Implement recurring payments and subscriptions Review payments, refunds and settlements Troubleshoot webhooks and authentication Upgrade Mollie SDKs and migrate from the Orders API Show in context →2 more matching sourcesPublisher description Mollie payment integration — connects Codex to your Mollie account via the Mollie MCP server and activates skills for payments, Mollie Connect, recurring payments, refunds/operations, troubleshooting, SDK upgrades, and building Mollie-pow… Show in context →Publisher full description Connects Codex to your Mollie account through the Mollie MCP server and adds skills for building Mollie integrations: hosted checkout and Components, Mollie Connect for platforms and marketplaces, recurring pa… Show in context → |
FinanceVersion 1.5.0 | View details → |
Platform Engineering CopilotKrishna Sathvik Publisher full description Platform Engineering Copilot helps you design, review, troubleshoot, and operate reliable cloud platforms across Kubernetes, containers, infrastructure as code, CI/CD, GitOps, networking, IAM, observability, SRE, and developer-platform workflows. It can review platform architecture, diagnose deployment and cluster incidents, design safer Terraform chang… Show in context →1 more matching sourcesPublisher capabilities · listing …eshoot Kubernetes, containers, networking, DNS, ingress, scheduling, rollout, and runtime incidents Review Kubernetes probes, requests, limits, disruption budgets, autoscaling, and workload availability Design safer Terraform plans, modules, state workflows, drift controls, approvals, and rollback s… Show in context → |
Developer ToolsVersion 0.1.0 | View details → |
Screenshot Action Inboxbattle-doll Publisher full description Organize a user-authorized batch, folder, or ZIP of screenshots into a reviewable action inbox. Extract candidate tasks, dates, events, receipts, and references; preserve source filenames; group duplicates; surface uncertainty; and prepare calendar-ready drafts. Use it w… …ingle-image creative edits, OCR-only transcription, email triage, surveillance, identity inference, code architecture analysis, or voice notifications. The plugin never creates calendar events, sends messages, deletes screenshots, or moves files. Its dependency-free processor writes deterministic lo… Show in context →2 more matching sourcesPublisher capabilities · listing …source screenshots Group duplicates and related items Surface dates, amounts, and uncertainty Draft reviewable calendar entries Propose reversible screenshot archiving Show in context →Publisher description …authorized screenshot batches into source-linked actions, duplicate groups, uncertainty flags, and review-only calendar drafts. Show in context → |
ProductivityVersion 1.0.2 | View details → |
stark AI Developerservrox solutions UG Publisher description …ngs practical workflows for implementation-ready specifications, architecture decisions, structural code analysis, editable diagrams, repository visuals, agent memory, and capability recommendations. Its open-source skills expose their instructions and supporting scripts for review and adaptation. The package has no shared backend, bundled MCP server, telemetry or analytics. Jev Capability Advisor is an optional Codex workflow: fresh recommendations send your supplied tas… Show in context →1 more matching sourcesPublisher capabilities · listing …ntation-ready specifications. Compare software architecture options with explicit tradeoffs. Search code structurally with CodeGraph and ast-grep workflows. Create editable draw.io diagrams from system context. Create repository documentation and animated README assets. Curate durable Codex memory w… Show in context → |
Developer ToolsVersion 1.7.1 | View details → |
URLMe.linkXZONDTECH Publisher full description …a branded custom domain, choose custom aliases, add a private description, and schedule expiration. Review recent links with destination, status, redirect count, last activity, device mix, and referrer mix. Update private descriptions, pause or resume redirects, permanently expire links, identify th… …reation, private tags and filtering, UTM parameters, destination updates, deletion, downloadable QR codes, CSV export, REST API automation with idempotent retries, per-integration API-key creation and revocation, and subscription management. Those wider features are available in the web console or R… Show in context →2 more matching sourcesPublisher capabilities · listing …links Use connected custom domains Choose custom aliases Schedule link expiration List recent links Review redirect analytics Label links privately Pause and resume links Permanently expire links Check plan usage Identify the connected workspace Show in context →Publisher description …ort links, inspect performance, and manage link lifecycles in your URLMe workspace from ChatGPT and Codex. Show in context → |
Developer ToolsVersion 1.0.2 | View details → |
Website Deploy ToolkitVineet Sriram Publisher full description …he people you list. Change a site any time by asking for it. Earlier versions are kept, so you can preview one or put it back. Saved data keeps 30 days of history, so a deleted entry or an unwanted change can be restored, and a deleted site can be brought back for 7 days. Ask how many people visited… …ad a copy of any site whenever you like. You sign in to Simple Host once (with Google or an emailed code); after that every conversation can publish and update your sites. Pages are public to anyone with the link, so keep private information in private lists. Free to start. Show in context →1 more matching sourcesPublisher capabilities · listing Publish websites, each at its own public address Edit, rename, preview, roll back and delete your sites Save form submissions, RSVPs, votes and orders Keep orders and sign-ups in private lists only you can read Read what your sites have collected, and undo changes… Show in context → |
ProductivityVersion 0.9.4 | View details → |
Yaps Video ClippingYaps AI Publisher full description …peech, removing dead air and long pauses, and exporting a separate MP4 without touching the source. Review the exact keep ranges and estimated result before rendering, choose Tight, Natural, or Relaxed pacing, adjust safe boundary padding, redetect only when detection settings change, and verify the… …, and FFmpeg before processing the selected video. Requires a local-capable ChatGPT Desktop Work or Codex session; ChatGPT web and cloud sessions cannot reach the installed Yaps engine. Users can also run Auto Cut directly in Yaps. Show in context →1 more matching sourcesPublisher capabilities · listing Remove dead air from video Trim long pauses Reviewable cut plans Tight, Natural, and Relaxed pacing Non-destructive MP4 export Local speech detection Verified output Show in context → |
CreativityVersion 0.1.5 | View details → |
YCloud Developer KitYCloud Developers Publisher full description …ns, appointment reminders, customer support, and lead capture into an integration plan, server-side code, and local tests. Get help with template and media messages, incoming messages and delivery-status webhooks, contacts and unsubscribe preferences, WhatsApp Flows, business accounts, phone numbers… …error handling, using YCloud API contracts and official documentation. Start from a new workflow or review an existing integration, then check its behavior with mocks and local sandbox tests for supported scenarios. Develop and validate locally; your application connects to YCloud at runtime using c… Show in context →2 more matching sourcesPublisher description …ness API integrations with YCloud: messaging, templates, media, contacts, Flows, and webhooks, with code and local tests for your app. Show in context → |
Developer ToolsVersion 0.7.9 | View details → |
Aivana CIO Decision TwinAivana GmbHEvidence-backed CIO decision support, option challenges and decision lifecycle reviews. Publisher keywords · listing …egulatory-shock capital-allocation cio-os-maturity stakeholder-alignment exception-waiver policy-as-code benefits-realization escalation-drafts control-tower data-trust architecture-runway executive-narrative decision-backlog due-diligence resilience customer-trust ai-portfolio cost-of-delay decisio… Show in context →3 more matching sourcesPublisher keywords · package …egulatory-shock capital-allocation cio-os-maturity stakeholder-alignment exception-waiver policy-as-code benefits-realization escalation-drafts control-tower data-trust architecture-runway executive-narrative decision-backlog due-diligence resilience customer-trust ai-portfolio cost-of-delay decisio… Show in context →Publisher description Evidence-backed CIO decision support, option challenges and decision lifecycle reviews. Show in context →Publisher full description …ence and human approval gates. Start with Board Prep, Crisis, Portfolio, AI Governance or Operating Review. Decision lifecycle guidance helps identify validity conditions, changed assumptions, stakeholder disagreements, reversible experiments and outcome evidence. Twin means a conditional decision m… Show in context → |
ProductivityVersion 0.1.1 | View details → |
Anti-ChurnOrbralUse before repeating an agent action to reuse matching evidence, allow valid changed work, and gate only the duplicate local action. Publisher keywords · listing agents codex duplicate-work evidence-reuse rate-limits receipts Show in context →1 more matching sourcesPublisher full description Use this before repeating an agent test, review, retry, tool call, or promotion check. Anti-Churn compares the proposed local action with accepted evidence, reuses matching results, permits changed work through typed invalidation, and shows… Show in context → |
Developer ToolsVersion 0.1.4 | View details → |
ArrowgramGetPaidX.com Publisher full description Arrowgram helps Codex initialize, edit, validate, preview, snapshot, and build file-backed Arrowgram workspaces using @hotdocx/arrowgram-agent. Show in context →2 more matching sourcesPublisher description Codex workflows for file-backed Arrowgram diagrams and papers. Show in context → |
Education & ResearchVersion 0.1.0+codex.20260806033509 | View details → |
Atbash SafetyAtbash AI Publisher full description Atbash Safety checks supported Codex tool calls against your Atbash agent's safety policy before execution. The package includes a local PreToolUse hook, the bundled production Atbash SDK, and a setup and troubleshooting skill; it… …ent private key and exact organization name in the local Atbash configuration file, then explicitly review and trust the hook in Codex. Never paste private keys into chat. Once configured, enabled, and trusted, the hook sends tool-call details through the SDK to Atbash for a judgment. ALLOW permits… Show in context →2 more matching sourcesPublisher description Automatically guards supported Codex tool calls with Atbash safety judgments and provides secure local setup guidance. Show in context → |
SecurityVersion 0.3.3 | View details → |
AtReadyRussell Lane Wonsley Publisher description Add declared resources through a preview-first conversation, then contribute resource-fit advice to Codex's plan. Show in context →2 more matching sourcesPublisher full description AtReady is a small resource-fit companion for supported Codex surfaces. Add one declared tool, service, subscription, person, or agent through a conversational no-write preview and a separate exact save approval. Then bring AtReady a goal, rough plan, or written plan before implementation to match saved tools, services, subscriptions, people, and agents to planner-pro… Show in context → |
Developer ToolsVersion 0.1.14 | View details → |
ChatGPT AdminOpenAI Publisher description …PT workspace owners and admins to manage members, groups, roles, permissions, GPTs, and Skills, and review Agents and audit logs. Monitor usage and billing across Chat, Codex, and Work, and manage usage limits and alerts. Guide alternative authentication and provider credential setup when available. Show in context →2 more matching sourcesPublisher full description …PT workspace owners and admins to manage members, groups, roles, permissions, GPTs, and Skills, and review Agents and audit logs. Monitor usage and billing across Chat, Codex, and Work, and manage usage limits and alerts. Available only in ChatGPT Work and Codex modes. Includes alternative-authentication setup guidance with explicit access choices, private credential… Show in context →Publisher keywords · listing admin-console agents alternative-authentication analytics audit-logs billing codex gpts groups invitations members permissions provider-setup roles service-accounts shared-links skills spending usage-limits workspace-administration Show in context → |
Business & OperationsVersion 0.1.26 | View details → |
Completion ReceiptOrbralRecord approved commands, selected file hashes, and Git state in local receipts you can verify later. Publisher keywords · listing agent-verification completion-receipts test-evidence build-proof git-drift coding-agents ci codex Show in context →1 more matching sourcesPublisher full description …ompletion Receipt when completed agent work or a release check needs a full record someone else can review. Using the supplied approved command and selected paths, it captures what ran, the result, selected file hashes, Git state, and later drift on those paths. It records observed evidence; it does… Show in context → |
Developer ToolsVersion 0.1.5 | View details → |
Dialogue SkillsKentaro Takemura対話の意図を保ち、論考・プロンプト・レビュー・掲載へつなぐ4つのスキル。 Publisher keywords · listing dialogue writing prompts review publishing Show in context →1 more matching sourcesPublisher full description …に掲載や更新を進めます。 各スキルは必要なものだけ単独で使えます。本文と付属の事例は日本語です。掲載先への接続や認証情報は同梱していません。掲載やファイル保存などの実行範囲は、利用するChatGPT・Codex環境のツールと権限に依存します。 論考とレビューでは、本文に加えて紹介するリンクや添付も対象とし、読者への有用性と会話の参加者にとっての適切さを確かめます。AIによるレビューは、誤りが一切ないことの保証ではありません。 Show in context → |
ProductivityVersion 0.1.0+codex.20260916024048 | View details → |
Endor Labs Agent KitEndor LabsEndor Labs security workflows and setup for Codex. Publisher keywords · listing endor-labs security sca sast codex Show in context →2 more matching sourcesPublisher full description …ged AppSec workflows for SCA remediation, AI SAST triage, CI/CD posture, malware response, findings review, Endor Labs setup, and more. Show in context → |
SecurityVersion 2.2.2 | View details → |
LuvusRiz Publisher full description Control a local Luvus session from Codex. Delegate work, fork agent sessions, arrange workspaces, review DIFF notes, coordinate tasks, and build capability-driven UHP automation. Requires an installed Luvus client and a running Luvus session. Show in context →2 more matching sourcesPublisher description Control Luvus agents, workspaces, and UHP automation from Codex. Show in context → |
ProductivityVersion 0.4.2 | View details → |
ProofreadRafael ArciniegasConservative proofreading and translation review that preserve meaning, voice, and protected content. Publisher keywords · listing proofreading copy-editing grammar translation-review writing Show in context →2 more matching sourcesPublisher description Conservative proofreading and translation review that preserve meaning, voice, and protected content. Show in context →Publisher full description …lling, clarity, style, and translated prose while preserving the writer's facts, voice, quotations, code, citations, and exact values. Show in context → |
ProductivityVersion 0.4.0 | View details → |
ServotabYifei Fang Publisher full description Servotab helps Codex plan, implement, debug, review, and verify repository work. It keeps clear changes direct, adds stronger method only when risk or uncertainty requires it, and closes claims with fresh evidence while preserving the complete r… Show in context →2 more matching sources |
Developer ToolsVersion 0.6.4 | View details → |
SkarnSkarn Software OÜ Publisher full description …ine and reports risky declarations: hooks, MCP servers, and permission grants that could run remote code or send data off the machine. Both passes run entirely on this machine and make no network call. Neither modifies a session transcript or a configuration file, and every credential value in the output is masked, so a finding names a rule and a masked preview and never the credential itself. Skarn surfaces findings and does not rotate a credential or edit a configuration on its own: the skill proposes, and the user decides. The one thing the skill c… Show in context →1 more matching sourcesPublisher keywords · listing security secrets credential-leak ai-coding-sessions audit codex Show in context → |
SecurityVersion 0.27.0 | View details → |
Skill Risk CheckOrbralScan agent skills and plugins locally for reviewable risk patterns before installation. Publisher keywords · listing plugin-security agent-skills pre-install-scan prompt-injection supply-chain sarif codex claude-code Show in context →1 more matching sourcesPublisher description Scan agent skills and plugins locally for reviewable risk patterns before installation. Show in context → |
SecurityVersion 0.1.5 | View details → |
TokenOS dApp BuilderTokenOS Publisher full description …dit estimate. One link opens the TokenOS Development Workspace with the prompt pre-filled — build, preview, deploy and host without leaving the browser. Tools: • plan_dapp — Turn the user's app idea into a spec (features, pages, components, data model, Web3 integrations, stack, steps, credit estimat… …generate solana app”; “ai web3 app builder”; “create nft minting website”; “build dao website”; “no code dapp builder”. Documentation: https://tokenos.ai/mcp/dapp-builder Outputs are informational — on-chain reads, deterministic calculators and heuristic scans — not financial, legal or security advi… Show in context →1 more matching sourcesPublisher keywords · listing …app with ai generate solana app ai web3 app builder create nft minting website build dao website no code dapp builder ai smart contract generator solana app generator Show in context → |
Developer ToolsVersion 1.0.3 | View details → |
UnicycleUnicycle Publisher full description Use native Codex voice to follow task changes, review previews, and send scoped decisions to existing owners. Private local cursor and delivery cache. Requires native task tools; synthesized voice selection remains host-controlled. Show in context →2 more matching sourcesPublisher description Coordinate existing Codex tasks from one native voice conversation. Show in context → |
ProductivityVersion 0.1.0+codex.20260906230521 | View details → |
Visual TruthDerek Hanchi Publisher full description …lti-selection, reusable components, data binding, opt-in privacy-first feedback, exact styling, and reviewable Make It Code output without shipping the editor overlay. Show in context →2 more matching sourcesPublisher keywords · listing visual-editor wysiwyg react vite responsive-design design-to-code codex Show in context →Publisher description Familiar Duda, Squarespace, and Elementor visual editing for local websites, with precise Codex code handoff. Show in context → |
ProductivityVersion 1.3.0 | View details → |
ZzzOpsDavid RzepaAgentic engineering with durable goals for autonomous coding agents Publisher keywords · listing …engineering coding-agents autonomous-development repository-bootstrap goal-management github-issues codex claude-code Show in context →1 more matching sourcesPublisher full description ZzzOps gives autonomous coding agents a reviewed, prioritized, and resumable agentic-engineering loop for repository bootstrapping and durable goals in GitHub Issues. It coordinates implementation only under reviewed project policy. Show in context → |
Developer ToolsVersion 2.1.0 | View details → |
FunlearnyNexcode Yazilim ve Teknoloji Anonim SirketiCreate multiple-choice quizzes from a topic or your lesson notes. Review 1–20 questions with 2–4 choices and one correct answer per quest... Publisher Nexcode Yazilim ve Teknoloji Anonim Sirketi Show in context →1 more matching sourcesPublisher description Create multiple-choice quizzes from a topic or your lesson notes. Review 1–20 questions with 2–4 choices and one correct answer per question, simplify them, or translate them. Open the preview in Funlearny, sign in, and choose Save to keep it as a private draft. Des… Show in context → |
Education & ResearchVersion 1.0.1 | View details → |
SourceFlagCodeArtisans LLCSourceFlag helps users scan direct public RFP PDF URLs from ChatGPT and receive a bounded readiness preview with deadline signals, mandat... Publisher CodeArtisans LLC Show in context →1 more matching sourcesPublisher description …ourceFlag helps users scan direct public RFP PDF URLs from ChatGPT and receive a bounded readiness preview with deadline signals, mandatory event signals, addenda and Q&A risk, missing-document warnings, bid/no-bid blockers, and sample compliance-matrix rows. Show in context → |
Business & OperationsVersion 1.0.0 | View details → |
Agentic Course RedesignGIAN PETER OCHSNER Publisher full description …ial Designer; Artefact Accessibility and Visual QA Auditor. The student-experience role is a design-review proxy and never authorises identifiable student data. ◆ GATED WORKFLOW • Gate 0A: verify ownership/processing authority, sensitivity, student data, protected assessment and environment before a… …a card only if the live host can show the complete option set plus custom answer. Verified current Codex in Plan mode: 2–3 explicit choices plus automatic Other. • If capacity is unknown, unavailable or exceeded, use ordinary chat with every valid numbered option plus Other, then wait. Never prune,… Show in context → |
Education & ResearchVersion 0.2.5 | View details → |
AI Software ArchitectAUTOSOFT Engineering Publisher description Project-aware design-pattern and architecture guidance using your Codex model, with transparent local safety and quality hooks. Show in context →1 more matching sourcesPublisher full description …s with guardrails, validated Architecture Decision Records (ADRs), coding handoffs, and conformance reviews using the user's selected AI model. ⚠️ IMPORTANT: BEFORE FIRST USE, ACTIVATE ALL FIVE BUNDLED HOOKS IN THE HOOKS SECTION BELOW. All five are required for reliable routing, continuation, safety… Show in context → |
Developer ToolsVersion 0.2.3 | View details → |
Annotations ExtensibilityOpenAI Publisher full description …h parts of the page they can select, add useful context to their comments, and offer controls that preview changes such as color, size, or visibility. Use public documentation to integrate page selection, custom controls, and canvas objects through your existing application code. Show in context →1 more matching sourcesPublisher description …he ChatGPT browser: choose what users can select, add context to comments, and offer controls that preview changes. Show in context → |
Developer ToolsVersion 0.1.1 | View details → |